Jump to ContentJump to Main Navigation
Show Summary Details
In This Section

International Journal of Chemical Reactor Engineering

Ed. by de Lasa, Hugo / Xu, Charles Chunbao

6 Issues per year


IMPACT FACTOR increased in 2015: 0.759

SCImago Journal Rank (SJR) 2015: 0.276
Source Normalized Impact per Paper (SNIP) 2015: 0.473
Impact per Publication (IPP) 2015: 0.636

Online
ISSN
1542-6580
See all formats and pricing
In This Section

Combined Mechanistic and Empirical Modelling

Belmiro Duarte
  • 1ISEC, Polytechnic Institute of Coimbra,
/ P. M. Saraiva
  • 2DEQ, Universidade de Coimbra,
/ C. C. Pantelides
  • 3Imperial College,
Published Online: 2004-01-15 | DOI: https://doi.org/10.2202/1542-6580.1128

We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors.

Keywords: Hybrid Modelling; Gray Box Modelling; Multivariate Adaptive Regression Splines

About the article

Published Online: 2004-01-15



Citation Information: International Journal of Chemical Reactor Engineering, ISSN (Online) 1542-6580, DOI: https://doi.org/10.2202/1542-6580.1128. Export Citation

Citing Articles

Here you can find all Crossref-listed publications in which this article is cited. If you would like to receive automatic email messages as soon as this article is cited in other publications, simply activate the “Citation Alert” on the top of this page.

[1]
Nuno Cosme, Marja Koski, and Michael Z. Hauschild
Ecological Modelling, 2015, Volume 317, Page 50
[2]
Francesco Baldi, Hannes Johnson, Cecilia Gabrielii, and Karin Andersson
Energy Procedia, 2014, Volume 61, Page 1732
[3]
Laurent Bourgois, Gilles Roussel, and Mohammed Benjelloun
Neural Networks, 2013, Volume 38, Page 90
[4]
Aidong Yang, Elaine Martin, and Julian Morris
Computers & Chemical Engineering, 2011, Volume 35, Number 1, Page 63

Comments (0)

Please log in or register to comment.
Log in